© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 6688
    Prev
    Next
    INDEX
    Explanations

    negative indicators or expressions of dissatisfaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    unit tests with utf-8 encoding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oredCriteria
    -0.62
     للمعارف
    -0.54
     Exactos
    -0.49
    
    -0.48
    XmlEnum
    -0.48
    PullParser
    -0.43
     democratic
    -0.43
    +#+#
    -0.42
    poque
    -0.41
    出版年
    -0.41
    POSITIVE LOGITS
     onCancelled
    0.43
     ProtoMessage
    0.42
    WriteTagHelper
    0.38
    田市
    0.35
    ﹍﹍﹍
    0.35
    KEYWORDS
    0.34
    })();
    0.32
    ametro
    0.32
    AddHtmlAttribute
    0.32
    });*/
    0.32
    Activations Density 0.001%

    No Known Activations